Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    included versions or variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Iodine
    0.45
    thiophene
    0.45
    ,.
    0.44
    .$.
    0.43
     iodine
    0.43
    .).
    0.43
    ).
    0.42
     fod
    0.42
     vnd
    0.42
     loader
    0.41
    POSITIVE LOGITS
    eren
    0.50
    ren
    0.49
    obic
    0.48
    ikki
    0.47
    ri
    0.46
    ḵ
    0.46
     tät
    0.46
    ত্রিম
    0.46
    គ្ន
    0.46
    enzi
    0.46
    Act Density 0.000%

    No Known Activations